dma-mapping: add a new dma_alloc_noncoherent API

Add a new API to allocate and free memory that is guaranteed to be
addressable by a device, but which potentially is not cache coherent
for DMA.

To transfer ownership to and from the device, the existing streaming
DMA API calls dma_sync_single_for_device and dma_sync_single_for_cpu
must be used.

For now the new calls are implemented on top of dma_alloc_attrs just
like the old-noncoherent API, but once all drivers are switched to
the new API it will be replaced with a better working implementation
that is available on all architectures.

Signed-off-by: Christoph Hellwig <hch@lst.de>

Documentation/core-api/dma-api.rst

@@ -516,48 +516,56 @@ routines, e.g.:::
 	}
 
 
-Part II - Advanced dma usage
+Part II - Non-coherent DMA allocations
-----------------------------
+--------------------------------------
 
-Warning: These pieces of the DMA API should not be used in the
+These APIs allow to allocate pages in the kernel direct mapping that are
-majority of cases, since they cater for unlikely corner cases that
+guaranteed to be DMA addressable.  This means that unlike dma_alloc_coherent,
-don't belong in usual drivers.
+virt_to_page can be called on the resulting address, and the resulting
+struct page can be used for everything a struct page is suitable for.
 
-If you don't understand how cache line coherency works between a
+If you don't understand how cache line coherency works between a processor and
-processor and an I/O device, you should not be using this part of the
+an I/O device, you should not be using this part of the API.
-API at all.
 
 ::
 
 	void *
-	dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+	dma_alloc_noncoherent(struct device *dev, size_t size,
-			gfp_t flag, unsigned long attrs)
+			dma_addr_t *dma_handle, enum dma_data_direction dir,
+			gfp_t gfp)
 
-Identical to dma_alloc_coherent() except that when the
+This routine allocates a region of <size> bytes of consistent memory.  It
-DMA_ATTR_NON_CONSISTENT flags is passed in the attrs argument, the
+returns a pointer to the allocated region (in the processor's virtual address
-platform will choose to return either consistent or non-consistent memory
+space) or NULL if the allocation failed.  The returned memory may or may not
-as it sees fit.  By using this API, you are guaranteeing to the platform
+be in the kernels direct mapping.  Drivers must not call virt_to_page on
-that you have all the correct and necessary sync points for this memory
+the returned memory region.
-in the driver should it choose to return non-consistent memory.
 
-Note: where the platform can return consistent memory, it will
+It also returns a <dma_handle> which may be cast to an unsigned integer the
-guarantee that the sync points become nops.
+same width as the bus and given to the device as the DMA address base of
+the region.
 
-Warning:  Handling non-consistent memory is a real pain.  You should
+The dir parameter specified if data is read and/or written by the device,
-only use this API if you positively know your driver will be
+see dma_map_single() for details.
-required to work on one of the rare (usually non-PCI) architectures
+
-that simply cannot make consistent memory.
+The gfp parameter allows the caller to specify the ``GFP_`` flags (see
+kmalloc()) for the allocation, but rejects flags used to specify a memory
+zone such as GFP_DMA or GFP_HIGHMEM.
+
+Before giving the memory to the device, dma_sync_single_for_device() needs
+to be called, and before reading memory written by the device,
+dma_sync_single_for_cpu(), just like for streaming DMA mappings that are
+reused.
 
 ::
 
 	void
-	dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
+	dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
-		       dma_addr_t dma_handle, unsigned long attrs)
+			dma_addr_t dma_handle, enum dma_data_direction dir)
 
-Free memory allocated by the dma_alloc_attrs().  All common
+Free a region of memory previously allocated using dma_alloc_noncoherent().
-parameters must be identical to those otherwise passed to dma_free_coherent,
+dev, size and dma_handle and dir must all be the same as those passed into
-and the attrs argument must be identical to the attrs passed to
+dma_alloc_noncoherent().  cpu_addr must be the virtual address returned by
-dma_alloc_attrs().
+the dma_alloc_noncoherent().
 
 ::
 
@@ -575,17 +583,6 @@ memory or doing partial flushes.
 	into the width returned by this call.  It will also always be a power
 	of two for easy alignment.
 
-::
-
-	void
-	dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-		       enum dma_data_direction direction)
-
-Do a partial sync of memory that was allocated by dma_alloc_attrs() with
-the DMA_ATTR_NON_CONSISTENT flag starting at virtual address vaddr and
-continuing on for size.  Again, you *must* observe the cache line
-boundaries when doing this.
-
 
 Part III - Debug drivers use of the DMA-API
 -------------------------------------------

include/linux/dma-mapping.h

@@ -384,6 +384,18 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev)
 }
 #endif /* CONFIG_HAS_DMA */
 
+static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	return dma_alloc_attrs(dev, size, dma_handle, gfp,
+			DMA_ATTR_NON_CONSISTENT);
+}
+static inline void dma_free_noncoherent(struct device *dev, size_t size,
+		void *vaddr, dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	dma_free_attrs(dev, size, vaddr, dma_handle, DMA_ATTR_NON_CONSISTENT);
+}
+
 static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {